Computer-implemented 3d model analysis method, electronic device, and non-transitory computer readable storage medium

Abstract

A computer-implemented 3D model analysis method includes: projecting, by a processing circuit, multiple sample points in a 3-dimensional model of a scene to one or more 2-dimensional planes in order to obtain one or more 2-dimensional images corresponding to the 3-dimensional model of the scene; performing, by the processing circuit, an object segmentation and classification based on the one or more 2-dimensional images to obtain 2-dimensional sematic information on the one or more 2-dimensional planes; and projecting, by the processing circuit, the 2-dimensional sematic information to the 3-dimensional model of the scene to identify one or more target objects in the scene.

What is claimed is: 
     
         1 . A computer-implemented 3D model analysis method, comprising:
 projecting, by a processing circuit, a plurality of sample points in a 3-dimensional model of a scene to one or more 2-dimensional planes in order to obtain one or more 2-dimensional images corresponding to the 3-dimensional model of the scene;   performing, by the processing circuit, an object segmentation and classification based on the one or more 2-dimensional images to obtain 2-dimensional sematic information on the one or more 2-dimensional planes; and   projecting, by the processing circuit, the 2-dimensional sematic information to the 3-dimensional model of the scene to identify one or more target objects in the scene.   
     
     
         2 . The computer-implemented 3D model analysis method of  claim 1 , further comprising:
 sampling, by the processing circuit, the 3-dimensional model by voxel scaling to obtain the plurality of sample points in the 3-dimensional model.   
     
     
         3 . The computer-implemented 3D model analysis method of  claim 1 , further comprising:
 labeling, by the processing circuit, the 3-dimensional model to indicate the one or more target objects identified in the scene according to an identification result.   
     
     
         4 . The computer-implemented 3D model analysis method of  claim 1 , further comprising:
 classifying, by the processing circuit, the one or more target objects based on a shape information, a color information, a depth information, a texture information, or a combination thereof.   
     
     
         5 . The computer-implemented 3D model analysis method of  claim 4 , further comprising:
 classifying, by the processing circuit, a first object of the one or more target objects to a first object type on the condition that the shape information, the color information, the depth information, the texture information, or the combination thereof matches one or more predetermined characteristics of the first object type; and   classifying, by the processing circuit, a second object of the one or more target objects to a second object type on the condition that the shape information, the color information, the depth information, the texture information, or the combination thereof matches the one or more predetermined characteristics of the second object type.   
     
     
         6 . The computer-implemented 3D model analysis method of  claim 1 , further comprising:
 projecting, by the processing circuit, the plurality of sample points to a plurality of 2-dimensional planes in order to obtain a plurality of 2-dimensional images, wherein the plurality of 2-dimensional images respectively corresponds to the scene viewed from a plurality of viewpoints.   
     
     
         7 . The computer-implemented 3D model analysis method of  claim 6 , wherein the plurality of viewpoints are arranged along a tracking line. 
     
     
         8 . An electronic device, comprising:
 a processing circuit;   a memory electrically connected to the processing circuit and configured to store a 3-dimensional model of a scene; and   one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processing circuit, the one or more programs comprising instructions for:   projecting a plurality of sample points in the 3-dimensional model to one or more 2-dimensional planes in order to obtain one or more 2-dimensional images corresponding to the 3-dimensional model of the scene;   performing an object segmentation and classification based on the one or more 2-dimensional images to obtain 2-dimensional sematic information on the one or more 2-dimensional planes; and   projecting the 2-dimensional sematic information to the 3-dimensional model of the scene to identify one or more target objects in the scene.   
     
     
         9 . The electronic device as claimed in  claim 8 , wherein the one or more programs further comprise instructions for:
 sampling the 3-dimensional model by voxel scaling to obtain the plurality of sample points in the 3-dimensional model.   
     
     
         10 . The electronic device as claimed in  claim 8 , wherein the one or more programs further comprise instructions for:
 labeling the 3-dimensional model to indicate the one or more target objects identified in the scene according to an identification result.   
     
     
         11 . The electronic device as claimed in  claim 8 , wherein the one or more programs further comprise instructions for:
 classifying the one or more target objects based on a shape information, a color information, a depth information, a texture information, or a combination thereof.   
     
     
         12 . The electronic device as claimed in  claim 11 , wherein the one or more programs further comprise instructions for:
 classifying a first object of the one or more target objects to a first object type on the condition that the shape information, the color information, the depth information, the texture information, or the combination thereof matches one or more predetermined characteristics of the first object type; and   classifying, by the processing circuit, a second object of the one or more target objects to a second object type on the condition that the shape information, the color information, the texture information, or the combination thereof matches the one or more predetermined characteristics of the second object type.   
     
     
         13 . The electronic device as claimed in  claim 8 , wherein the one or more programs further comprise instructions for:
 projecting, by the processing circuit, the plurality of sample points to a plurality of 2-dimensional planes in order to obtain a plurality of 2-dimensional images, wherein the plurality of 2-dimensional images respectively corresponds to the scene viewed from a plurality of viewpoints.   
     
     
         14 . The electronic device as claimed in  claim 13 , wherein the plurality of viewpoints are arranged along a tracking line. 
     
     
         15 . A non-transitory computer readable storage medium storing one or more programs, comprising instructions, which when executed, causes a processing circuit to perform operations comprising:
 projecting a plurality of sample points in a 3-dimensional model of a scene to one or more 2-dimensional planes in order to obtain one or more 2-dimensional images corresponding to the 3-dimensional model of the scene;   performing an object segmentation and classification based on the one or more 2-dimensional images to obtain 2-dimensional sematic information on the one or more 2-dimensional planes; and   projecting the 2-dimensional sematic information to the 3-dimensional model of the scene to identify one or more target objects in the scene.   
     
     
         16 . The non-transitory computer readable storage medium as claimed in  claim 15 , further comprising instructions, which when executed, causes the processing circuit to further perform operations comprising:
 sampling the 3-dimensional model by voxel scaling to obtain the plurality of sample points in the 3-dimensional model.   
     
     
         17 . The non-transitory computer readable storage medium as claimed in  claim 15 , further comprising instructions, which when executed, causes the processing circuit to further perform operations comprising:
 labeling the 3-dimensional model to indicate the one or more target objects identified in the scene according to an identification result.   
     
     
         18 . The non-transitory computer readable storage medium as claimed in  claim 15 , further comprising instructions, which when executed, causes the processing circuit to further perform operations comprising:
 classifying the one or more target objects based on a shape information, a color information, a depth information, a texture information, or a combination thereof.   
     
     
         19 . The non-transitory computer readable storage medium as claimed in  claim 18 , further comprising instructions, which when executed, causes the processing circuit to further perform operations comprising:
 classifying a first object of the one or more target objects to a first object type on the condition that the shape information, the color information, the depth information, the texture information, or the combination thereof matches one or more predetermined characteristics of the first object type; and   classifying, by the processing circuit, a second object of the one or more target objects to a second object type on the condition that the shape information, the color information, the depth information, the texture information, or the combination thereof matches the one or more predetermined characteristics of the second object type.   
     
     
         20 . The non-transitory computer readable storage medium as claimed in  claim 15 , further comprising instructions, which when executed, causes the processing circuit to further perform operations comprising:
 projecting, by the processing circuit, the plurality of sample points to a plurality of 2-dimensional planes in order to obtain a plurality of 2-dimensional images, wherein the plurality of 2-dimensional images respectively corresponds to the scene viewed from a plurality of viewpoints.